blocker
EmbeddingBlocker
Bases: SchemaAgnosticBlocker
Base class for embedding-based blocking approaches.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
frame_encoder |
HintOrType[FrameEncoder]
|
Encoder class to use for embedding the datasets. |
None
|
frame_encoder_kwargs |
OptionalKwargs
|
keyword arguments for initialising encoder class. |
None
|
embedding_block_builder |
HintOrType[EmbeddingBlockBuilder]
|
Block building class to create blocks from embeddings. |
None
|
embedding_block_builder_kwargs |
OptionalKwargs
|
keyword arguments for initalising blockbuilder. |
None
|
save |
bool
|
If true saves the embeddings before using blockbuilding. |
True
|
save_dir |
Optional[Union[str, Path]]
|
Directory where to save the embeddings. |
None
|
force |
bool
|
If true, recalculate the embeddings and overwrite existing. Else use precalculated if present. |
False
|
Attributes:
Name | Type | Description |
---|---|---|
frame_encoder |
Encoder class to use for embedding the datasets. |
|
embedding_block_builder |
Block building class to create blocks from embeddings. |
|
save |
If true saves the embeddings before using blockbuilding. |
|
save_dir |
Directory where to save the embeddings. |
|
force |
If true, recalculate the embeddings and overwrite existing. Else use precalculated if present. |
Source code in klinker/blockers/embedding/blocker.py
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
|
from_encoded(left_path=None, right_path=None, left_name=None, right_name=None)
Apply blockbuilding strategy from precalculated embeddings.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
left_path |
path of left encoding. |
None
|
|
right_path |
path of right encoding. |
None
|
|
left_name |
Name of left dataset. |
None
|
|
right_name |
Name of right dataset. |
None
|
Returns:
Type | Description |
---|---|
KlinkerBlockManager
|
Calculated blocks. |
Source code in klinker/blockers/embedding/blocker.py
200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
|
save_encoded(save_dir, encodings, table_names)
staticmethod
Save embeddings.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
save_dir |
Union[str, Path]
|
Union[str, pathlib.Path]: Directory to save into. |
required |
encodings |
Tuple[NamedVector, NamedVector]
|
Tuple[NamedVector, NamedVector]: Tuple of named embeddings. |
required |
table_names |
Tuple[str, str]
|
Tuple[str, str]: Name of left/right dataset. |
required |
Source code in klinker/blockers/embedding/blocker.py
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
|